Division of Surgical Oncology, Department of Surgery, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA.
Joint Department of Biomedical Engineering, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA.
Ann Surg Oncol. 2023 Nov;30(12):7107-7115. doi: 10.1245/s10434-023-14083-1. Epub 2023 Aug 10.
Intraoperative specimen mammography is a valuable tool in breast cancer surgery, providing immediate assessment of margins for a resected tumor. However, the accuracy of specimen mammography in detecting microscopic margin positivity is low. We sought to develop an artificial intelligence model to predict the pathologic margin status of resected breast tumors using specimen mammography.
A dataset of specimen mammography images matched with pathologic margin status was collected from our institution from 2017 to 2020. The dataset was randomly split into training, validation, and test sets. Specimen mammography models pretrained on radiologic images were developed and compared with models pretrained on nonmedical images. Model performance was assessed using sensitivity, specificity, and area under the receiver operating characteristic curve (AUROC).
The dataset included 821 images, and 53% had positive margins. For three out of four model architectures tested, models pretrained on radiologic images outperformed nonmedical models. The highest performing model, InceptionV3, showed sensitivity of 84%, specificity of 42%, and AUROC of 0.71. Model performance was better among patients with invasive cancers, less dense breasts, and non-white race.
This study developed and internally validated artificial intelligence models that predict pathologic margins status for partial mastectomy from specimen mammograms. The models' accuracy compares favorably with published literature on surgeon and radiologist interpretation of specimen mammography. With further development, these models could more precisely guide the extent of resection, potentially improving cosmesis and reducing reoperations.
术中标本乳腺 X 线摄影术是乳腺癌手术中的一种有价值的工具，可对切除肿瘤的切缘进行即时评估。然而，标本乳腺 X 线摄影术检测切除肿瘤的组织学切缘阳性的准确性较低。我们试图开发一种人工智能模型，利用标本乳腺 X 线摄影术预测切除乳腺肿瘤的病理切缘状态。
我们从 2017 年至 2020 年从我们的机构收集了一个与病理切缘状态匹配的标本乳腺 X 线摄影图像数据集。数据集被随机分为训练集、验证集和测试集。开发了基于放射图像预训练的标本乳腺 X 线摄影术模型，并与基于非医学图像预训练的模型进行了比较。使用敏感性、特异性和接受者操作特征曲线下的面积（AUROC）评估模型性能。
数据集包括 821 张图像，其中 53%的图像具有阳性切缘。在所测试的四种模型结构中的三种中，基于放射图像预训练的模型优于非医学模型。表现最好的模型为 InceptionV3，其敏感性为 84%，特异性为 42%，AUROC 为 0.71。在浸润性癌患者、乳腺密度较低和非白种人群中，模型性能更好。
本研究开发并内部验证了人工智能模型，可从标本乳腺 X 线摄影术预测保乳手术的病理切缘状态。这些模型的准确性与文献中报道的外科医生和放射科医生对标本乳腺 X 线摄影术的解读相媲美。随着进一步的发展，这些模型可以更精确地指导切除范围，有可能改善美容效果并减少再次手术。
